CN106056591A - Method for estimating urban density through fusion of optical spectrum image and laser radar data - Google Patents

Method for estimating urban density through fusion of optical spectrum image and laser radar data Download PDF

Info

Publication number
CN106056591A
CN106056591A CN201610356309.3A CN201610356309A CN106056591A CN 106056591 A CN106056591 A CN 106056591A CN 201610356309 A CN201610356309 A CN 201610356309A CN 106056591 A CN106056591 A CN 106056591A
Authority
CN
China
Prior art keywords
point
laser radar
radar data
building
area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610356309.3A
Other languages
Chinese (zh)
Other versions
CN106056591B (en
Inventor
谷延锋
王青旺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Heilongjiang Industrial Technology Research Institute Asset Management Co ltd
Original Assignee
Harbin Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Harbin Institute of Technology filed Critical Harbin Institute of Technology
Priority to CN201610356309.3A priority Critical patent/CN106056591B/en
Publication of CN106056591A publication Critical patent/CN106056591A/en
Application granted granted Critical
Publication of CN106056591B publication Critical patent/CN106056591B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J3/2823—Imaging spectrometer
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J3/2823—Imaging spectrometer
    • G01J2003/2826—Multispectral imaging, e.g. filter imaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10036—Multispectral image; Hyperspectral image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Landscapes

  • Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Image Processing (AREA)

Abstract

A method for estimating an urban density through a fusion of an optical spectrum image and laser radar data relates to the field of digital image processing. The method aims to solve the problems, existing in an existing urban density estimation method, that a used two-dimensional index is single, used three-dimensional indexes are less, and then the urban density cannot be reasonably and comprehensively evaluated. The method is performed according to the following steps: 1, obtaining a multispectral/hyperspectral image and laser radar data, preprocessing the two kinds of the data respectively, and generating a digital surface model by utilizing the laser radar data; 2, extracting optical spectrum information and space information from the multispectral/hyperspectral image, and extracting height information from the laser radar data; 3, inputting the extracted optical spectrum information, space information and height information into a classifier to obtain a classification theme map; and 4, performing an urban density index calculation using the classification theme map and the height information provided by a laser radar, and finally generating an urban density theme map. The method for estimating the urban density through the fusion of the optical spectrum image and the laser radar data can be applied to the field of the digital image processing.

Description

A kind of fusion spectrum picture and laser radar data carry out city density method of estimation
Technical field
The invention belongs to digital image processing field, belong to digital image processing field, particularly relate to a kind of fusion spectrum Image and laser radar data carry out city density method of estimation.
Background technology
Many/high spectrum image (multispectral or high spectrum image) is provided that the spectrum and spatial information, laser that target is abundant Radar is provided that the accurate elevation information of target.Many/high spectrum image and laser are provided from the information viewpoint provided Radar data has message complementary sense advantage.Both data sources of associating have obtained extensively in fields such as agricultural, forestry, urban development plannings General application.
City, as the product of human development, along with the increase of population, scientific and technological progress, is constantly expanding.Occupation of land face, city Long-pending increase, it is meant that the minimizing of cultivated area.Countries in the world use city vertical direction development tactics to alleviate this one after another Contradiction, therefore regardless of the commercial center in city, or residential block all occurs in that a large amount of high buildings and large mansions.Make just with tradition Space two-dimensional urban development density index city density is evaluated not rationally, it is necessary to consider the height of city vertical direction Degree information.This has promoted to combine the spectrum utilizing many/high spectrum image to provide and space two-dimensional information and laser radar data carries The vertical direction elevation information of confession carries out city density estimation.
In order to calculate city density index, it is necessary to first obtain atural object and cover thematic map.If three-dimensional (3-D) index is also Must be known by the elevation information of correspondence.Can be a pixel, a net for calculating the area-of-interest of city density index Lattice, the circle specifying radius or other self-defined shape.If using single pixel as area-of-interest, then can only calculate Two dimension (2-D) city density index, mixes technology by spectrum solution and calculates the ratio shared by specific atural object in sub-pixel level.With When other area-of-interest calculates object as index, researchers propose many 2-D indexs to evaluate city density: if not Water impermeable surface area, building coverage rate, vegetation coverage etc.；Relative to 2-D index, 3-D index is little, as vegetation volume, Building volume.
The problem that 2-D index is single, 3-D index is few of utilization is there is at present, it is impossible to close in city density estimates application Reason, thoroughly evaluating city density.For this problem existed, the present invention combines the many/high spectrum image of utilization and laser radar Data calculate can the 3-D index of rational evaluation city density, and combine 2-D and 3-D index city density more rationally commented Valency.
Summary of the invention
The present invention solves in existing city density method of estimation, the 2-D index that there is utilization is single, 3-D index is few, nothing Method rationally, the problem of thoroughly evaluating city density, and propose a kind of merge spectrum picture and laser radar data to carry out city close Degree method of estimation.
A kind of fusion spectrum picture and laser radar data carry out city density method of estimation, sequentially include the following steps:
One, obtain many/high spectrum image and laser radar data, respectively two kinds of data sources are carried out pretreatment, utilize and swash Optical radar data genaration digital surface model (DSM), and in two kinds of data sources, select control point, above two data source is entered Row registration；
Wherein, spectrum picture pretreatment is corrected and Geometry rectification for radiation；It is unusual to laser radar data pretreatment Point is rejected and image tiles；
Two, on many/high spectrum image, extract spectral information and spatial information, laser radar data extracts height letter Breath:
Wherein spectral information includes original spectrum wave band, normalized differential vegetation index and normalization building index, spatial information Including the space characteristics by using average, variance, morphology and Gabor spatial filter to generate；On laser radar data Extracting elevation information is normalization digital surface model；
Three, the spectral information, spatial information and the elevation information that extraction are obtained are input in grader, obtain classification scheme Figure；
Four, combine the elevation information utilizing classification scheme figure and laser radar to provide and carry out city density index calculating, Become city density thematic map throughout one's life；
Wherein city density index includes that 2-D and 3-D index, 2-D index are vegetation coverage and artificial surfaces coverage rate； 3-D index is building floor space and the ratio of usable floor area and building collection exponentially.
The present invention includes following beneficial effect:
1, due to the elevation information that make use of laser radar data to provide, 3-D index that can be reasonable in design, the mesh overcome The problem that the 3-D index of front existence lacks；
2, carrying out city density when evaluating, the present invention combines that to make use of 2-D and 3-D index to carry out city density more reasonable Evaluate, overcome tradition and use single index to be evaluated the unreasonable problem existed.
Accompanying drawing explanation
Fig. 1 is the method for the invention schematic flow sheet.
Detailed description of the invention
Understandable for enabling the above-mentioned purpose of the present invention, feature and advantage to become apparent from, below in conjunction with Fig. 1 and being embodied as The present invention is further detailed explanation for mode.
A kind of fusion spectrum picture and laser radar data described in detailed description of the invention one, present embodiment carry out city Density estimation method, sequentially includes the following steps:
One, obtain many/high spectrum image and laser radar data, respectively two kinds of data sources are carried out pretreatment, utilize and swash Optical radar data genaration digital surface model (DSM), and in two kinds of data sources, select control point, above two data source is entered Row registration；
Wherein, spectrum picture pretreatment is corrected and Geometry rectification for radiation；It is unusual to laser radar data pretreatment Point is rejected and image tiles；
Two, on many/high spectrum image, extract spectral information and spatial information, laser radar data extracts height letter Breath:
Wherein spectral information includes original spectrum wave band, normalized differential vegetation index and normalization building index, spatial information Including the space characteristics by using average, variance, morphology and Gabor spatial filter to generate；On laser radar data Extracting elevation information is normalization digital surface model；
Three, the spectral information, spatial information and the elevation information that extraction are obtained are input in grader, obtain classification scheme Figure；
Four, combine the elevation information utilizing classification scheme figure and laser radar to provide and carry out city density index calculating, Become city density thematic map throughout one's life；
Wherein city density index includes that 2-D and 3-D index, 2-D index are vegetation coverage and artificial surfaces coverage rate； 3-D index is building floor space and the ratio of usable floor area and building collection exponentially.
Present embodiment includes following beneficial effect:
1, due to the elevation information that make use of laser radar data to provide, 3-D index that can be reasonable in design, the mesh overcome The problem that the 3-D index of front existence lacks；
2, carrying out city density when evaluating, present embodiment is combined and be make use of 2-D and 3-D index to carry out city density more Rational evaluation, overcomes tradition and uses single index to be evaluated the unreasonable problem existed.
Detailed description of the invention two, present embodiment are to a kind of fusion spectrum picture described in detailed description of the invention one and to swash Optical radar data carry out further illustrating of city density method of estimation, and the control point described in step one is road junction, Or the flex point of building.
Detailed description of the invention three, present embodiment are to a kind of fusion spectrum picture described in detailed description of the invention one or two Carrying out further illustrating of city density method of estimation with laser radar data, the laser radar data described in step one is unusual Point refers to that height that the objects such as the bird due to airflight, floating rubbish and kite cause, apparently higher than the some cloud of atural object, is adopted Carry out the unusual cloud data of laser radar by statistics with histogram method to reject.
Detailed description of the invention four, present embodiment are to a kind of fusion spectrum one of detailed description of the invention one to three Suo Shu Image and laser radar data carry out further illustrating of city density method of estimation, the normalization numeral table described in step 2 Surface model calculates as follows:
1, lidar image filtering based on mobile Quadratic Surface Fitting, is divided into the point set in digital surface model Ground point and non-ground points two parts, being embodied as step is:
A, choosing suitable filter window size m × n, wherein the size of m and n is 102The rice order of magnitude；
B, in this window, choose minimum 10 point, as initial seed point, be input in the point set P of ground, this 10 points must be the point that on ground, object is constituted；
C, utilizing the point in point set P to carry out at Quadratic Surface Fitting, the functional equation involved by matching is:
Z i = c 0 + c 1 x i + c 2 y i + c 3 x i y i + c 4 x i 2 + c 5 y i 2
Wherein, (xi,yi) it is i-th point coordinate in the picture, ZiFor the height value that this point is corresponding；
Point input in being gathered by P successively, obtains a series of equation group, solves each coefficient under criterion of least squares c0,c1,...,c5, so that it is determined that surface equation；
Other height put are predicted by the surface equation that d, utilization obtain, if the difference of predictive value and actual value is more than threshold Value T, then judge that this point is as non-ground points；Otherwise, then this point is ground point, then joins in the point set P of ground by this point, again Calculate each coefficient, obtain new curved surface, be so repeated up to the most all judge complete；
E, moving window, to other position of image, complete the filtering of entire image；
2, the generation of normalization digital surface model:
The algorithm using inverse distance weighted interpolation carries out height interpolation, during interpolation gives the ground point near away from interpolation point Bigger weights, first centered by interpolated point, determine proper number N0Nearest neighbor point as source sampling point, it is assumed that interpolated point For S0(x0,y0), sampled point is Qi(xi,yi,zi), i=(1,2 ..., N0), the mathematic(al) representation of inverse distance-weighting average interpolation As follows:
Z S 0 = Σ i = 1 N 0 λ i Z i
WhereinHeight Estimation value for interpolated point；λiWeights for ith sample point；ZiHeight for ith sample point Angle value, λiAnd ZiTried to achieve by below equation:
diDistance for ith sample point to interpolated point:
d i = ( x i - x 0 ) 2 + ( y i - y 0 ) 2
Wherein p is positive integer, and when p value is 2, the effect of interpolation is best；
After completing Interpolation Process, i.e. generating digital terrain model (DTM), then subtracting each other with DSM Yu DTM is exactly normalization number Word table surface model.
Detailed description of the invention five, present embodiment are to a kind of fusion spectrum one of detailed description of the invention one to four Suo Shu Image and laser radar data carry out further illustrating of city density method of estimation, and the grader described in step 3 is decision-making Tree, support vector machine or neutral net.
Detailed description of the invention six, present embodiment are to a kind of fusion spectrum one of detailed description of the invention one to five Suo Shu Image and laser radar data carry out further illustrating of city density method of estimation, and the vegetation coverage described in step 4 is pressed Equation below calculates:
V F = A t + A g A A O I
Wherein, VF is vegetation coverage, AtFor the region area covered by trees in area-of-interest, AgFor region of interest The region area covered by grass and shrub in territory, AAOIArea for area-of-interest；
Described artificial surfaces coverage rate calculates as follows:
A S C = A b + A i A A O I
Wherein, ASC is artificial surfaces coverage rate, AbFor the region area covered by building in area-of-interest, AiFor sense By the artificial earth's surface such as road, square occupied area in interest region；
Described building floor space is calculated as follows with the ratio of usable floor area:
i F A R = A a b A f l
Wherein, AabFor building floor space, AflFor building usable floor area, it is assumed here that every floor is high 3 meters, floor Number N is pressed formula and is calculated:Calculate, wherein HBRefer to that building is high,Represent and round downwards；Building usable floor area presses formula Calculate:WhereinArea for every floor；
Described building collection exponentially is calculated as follows:
B A = A b A A O I M e d i a n ( D b ) - M e d i a n ( i F A R ) N b
Wherein, DbFor the distance between two solitary building centers every in area-of-interest, Median represents and takes intermediate value, NbFor Building number in area-of-interest.
Detailed description of the invention seven, present embodiment are to a kind of fusion spectrum one of detailed description of the invention one to six Suo Shu Image and laser radar data carry out further illustrating of city density method of estimation, generate city density master described in step 4 The particular content of topic figure is: each pixel is calculating center, 250 meters be the border circular areas of radius be the sense of corresponding center pixel Interest region carries out city density (UD) and estimates, calculates as follows:
UD=(BA+ASC)-(VF+iFAR)
Wherein, by vegetation coverage, artificial surfaces coverage rate, the ratio of building floor space and usable floor area and building Collection exponentially substitutes into before city density estimation formulas calculates and is all normalized to 0 to 1, and the UD value finally given is interval is [-2,2], Value is the biggest, and to represent city density the biggest.

Claims (7)

1. a fusion spectrum picture and laser radar data carry out city density method of estimation, it is characterised in that according to the following steps Carry out:
One, obtain many/high spectrum image and laser radar data, respectively two kinds of data sources are carried out pretreatment, utilize laser thunder Reach data genaration digital surface model DSM, and in two kinds of data sources, select control point, above two data source is joined Accurate；
Wherein, spectrum picture pretreatment is corrected and Geometry rectification for radiation；It is that singular point picks to laser radar data pretreatment Remove and image tiles；
Two, on many/high spectrum image, spectral information and spatial information are extracted, extraction elevation information on laser radar data:
Wherein spectral information includes original spectrum wave band, normalized differential vegetation index and normalization building index, and spatial information includes By the space characteristics using average, variance, morphology and Gabor spatial filter to generate；Laser radar data extracts Elevation information is normalization digital surface model；
Three, spectral information extraction obtained and spatial information are input in grader, obtain classification scheme figure；
Four, combine the elevation information utilizing classification scheme figure and laser radar to provide and carry out city density index calculating, the most throughout one's life Become city density thematic map；
Wherein city density index includes that 2-D and 3-D index, 2-D index are vegetation coverage and artificial surfaces coverage rate；3-D Index is building floor space and the ratio of usable floor area and building collection exponentially.
2. a kind of fusion spectrum picture as claimed in claim 1 and laser radar data carry out city density method of estimation, its It is characterised by that the control point described in step one is road junction, or the flex point of building.
3. a kind of fusion spectrum picture as claimed in claim 1 or 2 and laser radar data carry out city density method of estimation, It is characterized in that the laser radar data singular point described in step one refers to the bird due to airflight, floating rubbish and wind The height that the objects such as zither cause, apparently higher than the some cloud of atural object, uses statistics with histogram method to carry out laser radar singular point cloud number According to rejecting.
4. a kind of fusion spectrum picture as claimed in claim 3 and laser radar data carry out city density method of estimation, its It is characterised by that the normalization digital surface model described in step 2 calculates as follows:
4.1, lidar image filtering based on mobile Quadratic Surface Fitting, has been divided into ground by the point set in digital surface model Cake and non-ground points two parts, being embodied as step is:
A, choosing suitable filter window size m × n, wherein the size of m and n is 102The rice order of magnitude；
B, in this window, choose minimum 10 point, as initial seed point, be input in the point set P of ground, these 10 Point must be the point that on ground, object is constituted；
C, utilizing the point in point set P to carry out at Quadratic Surface Fitting, the functional equation involved by matching is:
Zi=c0+c1xi+c2yi+c3xiyi+c4xi 2+c5yi 2
Wherein, (xi,yi) it is i-th point coordinate in the picture, ZiFor the height value that this point is corresponding；
Point input in being gathered by P successively, obtains a series of equation group, solves each coefficient c under criterion of least squares0, c1,...,c5, so that it is determined that surface equation；
Other height put are predicted by the surface equation that d, utilization obtain, if the difference of predictive value and actual value is more than threshold value T, Then judge that this point is as non-ground points；Otherwise, then this point is ground point, is then joined in the point set P of ground by this point, recalculates Each coefficient, obtains new curved surface, be so repeated up to the most all judge complete；
E, moving window, to other position of image, complete the filtering of entire image；
4.2, the generation of normalization digital surface model:
The algorithm using inverse distance weighted interpolation carries out height interpolation, gives bigger to the ground point near away from interpolation point during interpolation Weights, first centered by interpolated point, determine proper number N0Nearest neighbor point as source sampling point, it is assumed that interpolated point is S0 (x0,y0), sampled point is Qi(xi,yi,zi), i=(1,2 ..., N0), the mathematic(al) representation of inverse distance-weighting average interpolation is such as Under:
Z S 0 = Σ i = 1 N 0 λ i Z i
WhereinHeight Estimation value for interpolated point；λiWeights for ith sample point；ZiFor the height value of ith sample point, λiAnd ZiTried to achieve by below equation:
diDistance for ith sample point to interpolated point:
d i = ( x i - x 0 ) 2 + ( y i - y 0 ) 2
Wherein p is positive integer；
After completing Interpolation Process, i.e. generating digital terrain model DTM, then subtracting each other with DSM Yu DTM is exactly normalization digital surface Model.
5. a kind of fusion spectrum picture as claimed in claim 4 and laser radar data carry out city density method of estimation, its It is characterised by that the grader described in step 3 is decision tree, support vector machine or neutral net.
6. a kind of fusion spectrum picture as claimed in claim 5 and laser radar data carry out city density method of estimation, its It is characterised by that the vegetation coverage described in step 4 calculates as follows:
V F = A t + A g A A O I
Wherein, VF is vegetation coverage, AtFor the region area covered by trees in area-of-interest, AgFor in area-of-interest The region area covered by grass and shrub, AAOIArea for area-of-interest；
Described artificial surfaces coverage rate calculates as follows:
A S C = A b + A i A A O I
Wherein, ASC is artificial surfaces coverage rate, AbFor the region area covered by building in area-of-interest, AiFor interested By road, artificial earth's surface, square occupied area in region；
Described building floor space is calculated as follows with the ratio of usable floor area:
i F A R = A a b A f l
Wherein, AabFor building floor space, AflFor building usable floor area, it is assumed here that every floor is high 3 meters, floor number N Calculate by formula:Calculate, wherein HBRefer to that building is high,Represent and round downwards；Building usable floor area is pressed formula and is calculated:WhereinArea for every floor；
Described building collection exponentially is calculated as follows:
B A = A b A A O I M e d i a n ( D b ) - M e d i a n ( i F A R ) N b
Wherein, DbFor the distance between two solitary building centers every in area-of-interest, Median represents and takes intermediate value, NbEmerging for sense Building number in interest region.
7. a kind of fusion spectrum picture as claimed in claim 6 and laser radar data carry out city density method of estimation, its It is characterised by that the particular content generating city density thematic map described in step 4 is: each pixel is calculating center, 250 meters The area-of-interest that border circular areas is corresponding center pixel for radius carries out city density UD estimation, counts as follows Calculate:
UD=(BA+ASC)-(VF+iFAR)
Wherein, by integrated with the ratio of usable floor area and building to vegetation coverage, artificial surfaces coverage rate, building floor space Index substitutes into before city density estimation formulas calculates and is all normalized to 0 to 1, and the UD value finally given is interval is [-2,2], and value is more Represent greatly city density the biggest.
CN201610356309.3A 2016-05-25 2016-05-25 A kind of fusion spectrum picture and laser radar data carry out city density estimation method Active CN106056591B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610356309.3A CN106056591B (en) 2016-05-25 2016-05-25 A kind of fusion spectrum picture and laser radar data carry out city density estimation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610356309.3A CN106056591B (en) 2016-05-25 2016-05-25 A kind of fusion spectrum picture and laser radar data carry out city density estimation method

Publications (2)

Publication Number Publication Date
CN106056591A true CN106056591A (en) 2016-10-26
CN106056591B CN106056591B (en) 2019-01-18

Family

ID=57175271

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610356309.3A Active CN106056591B (en) 2016-05-25 2016-05-25 A kind of fusion spectrum picture and laser radar data carry out city density estimation method

Country Status (1)

Country Link
CN (1) CN106056591B (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529484A (en) * 2016-11-16 2017-03-22 哈尔滨工业大学 Combined spectrum and laser radar data classification method based on class-fixed multinucleated learning
CN107092020A (en) * 2017-04-19 2017-08-25 北京大学 Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image
CN107392130A (en) * 2017-07-13 2017-11-24 西安电子科技大学 Classification of Multispectral Images method based on threshold adaptive and convolutional neural networks
CN107657206A (en) * 2016-12-23 2018-02-02 航天星图科技（北京）有限公司 A kind of method based on remote sensing technology estimation forest coverage rate
CN108020324A (en) * 2017-11-07 2018-05-11 湖北理工学院 The filter detecting method of single beam laser superimposed pulse signal
CN108334819A (en) * 2017-01-17 2018-07-27 德尔福技术有限公司 Ground classifier system for automated vehicle
CN108846352A (en) * 2018-06-08 2018-11-20 广东电网有限责任公司 A kind of vegetation classification and recognition methods
CN110427857A (en) * 2019-07-26 2019-11-08 国网湖北省电力有限公司检修公司 A kind of transmission line of electricity geological disasters analysis method based on Remote Sensing Data Fusion Algorithm
CN111257882A (en) * 2020-03-19 2020-06-09 北京三快在线科技有限公司 Data fusion method and device, unmanned equipment and readable storage medium
CN111638185A (en) * 2020-05-09 2020-09-08 哈尔滨工业大学 Remote sensing detection method based on unmanned aerial vehicle platform
CN111679287A (en) * 2020-06-05 2020-09-18 中国科学院空天信息创新研究院 Active video three-dimensional hyperspectral imaging method
CN111861170A (en) * 2020-07-07 2020-10-30 河南大学 Carbon emission space mapping method, density space distribution determining method and device
CN112130169A (en) * 2020-09-23 2020-12-25 广东工业大学 Point cloud level fusion method for laser radar data and hyperspectral image
CN112419402A (en) * 2020-11-27 2021-02-26 广东电网有限责任公司肇庆供电局 Positioning method and system based on multispectral image and laser point cloud
CN112859108A (en) * 2021-01-28 2021-05-28 中国科学院南京土壤研究所 Method for extracting under-forest vegetation coverage under complex terrain condition by using ground laser radar data
CN115906476A (en) * 2022-11-18 2023-04-04 国网湖北省电力有限公司经济技术研究院 Mountain land photovoltaic power generation capacity calculation method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5659391A (en) * 1996-01-26 1997-08-19 The United States Of America As Represented By The Secretary Of The Army Earth monitoring satellite system with combined infrared interferometry and photopolarimetry for chemical and biological sensing
CA2547359A1 (en) * 2003-11-26 2005-06-16 Florida Environmental Research Institute, Inc. Spectral imaging system
CN101866385A (en) * 2010-06-24 2010-10-20 浙江大学 Target parcel ground surface temperature simulation and optimization method
CN101894210A (en) * 2010-06-24 2010-11-24 浙江大学 Method for acquiring block energy conservation quantity based on three-dimensional scene images

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5659391A (en) * 1996-01-26 1997-08-19 The United States Of America As Represented By The Secretary Of The Army Earth monitoring satellite system with combined infrared interferometry and photopolarimetry for chemical and biological sensing
CA2547359A1 (en) * 2003-11-26 2005-06-16 Florida Environmental Research Institute, Inc. Spectral imaging system
CN101866385A (en) * 2010-06-24 2010-10-20 浙江大学 Target parcel ground surface temperature simulation and optimization method
CN101894210A (en) * 2010-06-24 2010-11-24 浙江大学 Method for acquiring block energy conservation quantity based on three-dimensional scene images

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
EMMANUEL BRATSOLIS等: "Automated Building Block Extraction and Building Density Classification Using Aerial Imagery and LiDAR Data", 《JOURNAL OF EARTH SCIENCE AND ENGINEERING》 *
冯凯: "基于多核学习的多/高光谱图像与激光雷达数据联合分类研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
满其霞: "激光雷达和高光谱数据融合的城市土地利用分类方法研究", 《中国博士学位论文全文数据库基础科学辑》 *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529484A (en) * 2016-11-16 2017-03-22 哈尔滨工业大学 Combined spectrum and laser radar data classification method based on class-fixed multinucleated learning
CN107657206A (en) * 2016-12-23 2018-02-02 航天星图科技（北京）有限公司 A kind of method based on remote sensing technology estimation forest coverage rate
CN108334819A (en) * 2017-01-17 2018-07-27 德尔福技术有限公司 Ground classifier system for automated vehicle
CN108334819B (en) * 2017-01-17 2021-12-03 安波福技术有限公司 Ground classifier system for automated vehicles
CN107092020A (en) * 2017-04-19 2017-08-25 北京大学 Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image
CN107092020B (en) * 2017-04-19 2019-09-13 北京大学 Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image
CN107392130B (en) * 2017-07-13 2020-12-08 西安电子科技大学 Multispectral image classification method based on threshold value self-adaption and convolutional neural network
CN107392130A (en) * 2017-07-13 2017-11-24 西安电子科技大学 Classification of Multispectral Images method based on threshold adaptive and convolutional neural networks
CN108020324A (en) * 2017-11-07 2018-05-11 湖北理工学院 The filter detecting method of single beam laser superimposed pulse signal
CN108846352A (en) * 2018-06-08 2018-11-20 广东电网有限责任公司 A kind of vegetation classification and recognition methods
CN108846352B (en) * 2018-06-08 2020-07-14 广东电网有限责任公司 Vegetation classification and identification method
CN110427857A (en) * 2019-07-26 2019-11-08 国网湖北省电力有限公司检修公司 A kind of transmission line of electricity geological disasters analysis method based on Remote Sensing Data Fusion Algorithm
CN111257882B (en) * 2020-03-19 2021-11-19 北京三快在线科技有限公司 Data fusion method and device, unmanned equipment and readable storage medium
CN111257882A (en) * 2020-03-19 2020-06-09 北京三快在线科技有限公司 Data fusion method and device, unmanned equipment and readable storage medium
CN111638185A (en) * 2020-05-09 2020-09-08 哈尔滨工业大学 Remote sensing detection method based on unmanned aerial vehicle platform
CN111638185B (en) * 2020-05-09 2022-05-17 哈尔滨工业大学 Remote sensing detection method based on unmanned aerial vehicle platform
CN111679287B (en) * 2020-06-05 2023-01-17 中国科学院空天信息创新研究院 Active video three-dimensional hyperspectral imaging method
CN111679287A (en) * 2020-06-05 2020-09-18 中国科学院空天信息创新研究院 Active video three-dimensional hyperspectral imaging method
CN111861170A (en) * 2020-07-07 2020-10-30 河南大学 Carbon emission space mapping method, density space distribution determining method and device
CN111861170B (en) * 2020-07-07 2023-08-04 河南大学 Carbon emission space drawing method, density space distribution determining method and device
CN112130169A (en) * 2020-09-23 2020-12-25 广东工业大学 Point cloud level fusion method for laser radar data and hyperspectral image
CN112130169B (en) * 2020-09-23 2022-09-16 广东工业大学 Point cloud level fusion method for laser radar data and hyperspectral image
CN112419402A (en) * 2020-11-27 2021-02-26 广东电网有限责任公司肇庆供电局 Positioning method and system based on multispectral image and laser point cloud
CN112859108A (en) * 2021-01-28 2021-05-28 中国科学院南京土壤研究所 Method for extracting under-forest vegetation coverage under complex terrain condition by using ground laser radar data
CN112859108B (en) * 2021-01-28 2024-03-22 中国科学院南京土壤研究所 Method for extracting vegetation coverage under forests under complex terrain condition by using ground laser radar data
CN115906476A (en) * 2022-11-18 2023-04-04 国网湖北省电力有限公司经济技术研究院 Mountain land photovoltaic power generation capacity calculation method
CN115906476B (en) * 2022-11-18 2023-09-01 国网湖北省电力有限公司经济技术研究院 Mountain photovoltaic power generation capacity calculation method

Also Published As

Publication number Publication date
CN106056591B (en) 2019-01-18

Similar Documents

Publication Publication Date Title
CN106056591A (en) Method for estimating urban density through fusion of optical spectrum image and laser radar data
CN108363983B (en) Urban vegetation classification method based on unmanned aerial vehicle image and reconstructed point cloud
CN104049245B (en) Urban building change detection method based on LiDAR point cloud spatial difference analysis
CN106780089B (en) Permanent basic farmland planning method based on neural network cellular automaton model
CN105677890B (en) A kind of green amount numerical map production in city and display methods
CN105608692B (en) Polarization SAR image segmentation method based on deconvolution network and sparse classification
CN109448016A (en) It is a kind of based on object-oriented and its be subordinate to rule remote sensing image tidal saltmarsh method
CN102902956B (en) A kind of ground visible cloud image identifying processing method
CN105118090B (en) A kind of point cloud filtering method of adaptive complicated landform structure
CN106951836A (en) Crop cover degree extracting method based on priori threshold optimization convolutional neural networks
CN102103202A (en) Semi-supervised classification method for airborne laser radar data fusing images
CN110990511B (en) Local climate zone classification method considering two-dimensional and three-dimensional forms of city
CN105389559A (en) System and method for identifying agricultural disaster scope based on high-resolution remote sensing image
CN104318270A (en) Land cover classification method based on MODIS time series data
CN103500344A (en) Method and module for extracting and interpreting information of remote-sensing image
CN116757357B (en) Land ecological condition assessment method coupled with multisource remote sensing information
CN106548141A (en) A kind of object-oriented farmland information extraction method based on the triangulation network
CN106683102A (en) SAR image segmentation method based on ridgelet filters and convolution structure model
CN109581412A (en) A kind of method of quick carry out soil erosion Dynamic Change by Remote Sensing monitoring
CN106611421A (en) SAR image segmentation method based on feature learning and sketch line constraint
CN108052876A (en) Regional development appraisal procedure and device based on image identification
CN109657569A (en) More vegetation areas transmission of electricity corridor hidden danger point quick extraction method based on cloud analysis
CN105069463A (en) Object-oriented multiple scale mountainous city land coverage information obtaining method
CN105447274A (en) Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology
CN106611423A (en) SAR image segmentation method based on ridge wave filter and deconvolution structural model

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20210118

Address after: Building 9, accelerator, 14955 Zhongyuan Avenue, Songbei District, Harbin City, Heilongjiang Province

Patentee after: INDUSTRIAL TECHNOLOGY Research Institute OF HEILONGJIANG PROVINCE

Address before: 150001 No. 92 West straight street, Nangang District, Heilongjiang, Harbin

Patentee before: HARBIN INSTITUTE OF TECHNOLOGY

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230221

Address after: 150027 Room 412, Unit 1, No. 14955, Zhongyuan Avenue, Building 9, Innovation and Entrepreneurship Plaza, Science and Technology Innovation City, Harbin Hi tech Industrial Development Zone, Heilongjiang Province

Patentee after: Heilongjiang Industrial Technology Research Institute Asset Management Co.,Ltd.

Address before: Building 9, accelerator, 14955 Zhongyuan Avenue, Songbei District, Harbin City, Heilongjiang Province

Patentee before: INDUSTRIAL TECHNOLOGY Research Institute OF HEILONGJIANG PROVINCE